Skip to main content
Search

# BaME

1 related articles

Subscribe to updates
  1. arXiv

    Speech enhancement returns to Mel: BaME beats a 331M DiT backbone with 2.9% of its parameters and finishes in a single generation step

    Generative speech enhancement has leaned on learnable latent representations and large generative backbones, making acoustic fidelity, perceptual quality and processing efficiency hard to hold at once. BaME treats the Mel spectrum again as a structured acoustic representation: a subband-aware Transformer backbone reaches better enhancement than a 331M DiT backbone using only 2.9% of its parameters and 66.6% of its computation, and a vocoder with a degraded-phase prior plus one-step fidelity-perception alignment fine-tuning gives strong objective and subjective results on DNS-Challenge, EARS, GSR and URGENT benchmarks.

You’re all caught up